Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of the country "America"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the root "amer," likely relating to the concept of America or American identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fax
    -0.87
    eded
    -0.71
    ŃĶ
    -0.69
    ĵĺ
    -0.68
    ftime
    -0.67
    aches
    -0.63
     Malfoy
    -0.63
    IGH
    -0.61
    aching
    -0.60
    orset
    -0.60
    POSITIVE LOGITS
    icans
    1.36
    ican
    1.34
    ICAN
    1.21
    gdala
    1.07
    gency
    1.06
    ilial
    0.97
    iens
    0.87
    icity
    0.84
    nesia
    0.82
    icas
    0.80
    Act Density 0.036%

    No Known Activations